Enquire MCP vs Agentcairn — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Enquire MCP vs Agentcairn
In-depth architectural comparison of the Enquire MCP and Agentcairn MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Enquire MCP
Knowledge & Memory · Local stdio
Quality: 57/100 (Good) | Auth: No auth required
Agentcairn
Knowledge & Memory · Local stdio
Quality: 56/100 (Good) | Auth: No auth required
Verdict Summary: Choose Enquire MCP if you need specialized Knowledge & Memory tools running via a local process. Choose Agentcairn if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Enquire MCP when:
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: Hybrid retrieval: BM25, ML embeddings, BGE reranker with RRF fusion, Supports Markdown, PDFs with Tesseract OCR, Canvas, Dataview, and Bases, Returns source paths, page citations, age_days, and stale flags.
You need dedicated capabilities in the Knowledge & Memory domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: Plain Markdown Obsidian vault as canonical memory store, Rebuildable DuckDB index for hybrid BM25, vector, and graph recall, Non-lossy memory capture with supersession and secret redaction.
Long-term memory for AI agents (Claude Code/Desktop, Cursor, ChatGPT, Codex, OpenClaw) backed by a local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantization, agentic RAG (HyDE + sub-question), GraphRAG-light (Louvain wikilink community detection), standalone Obsidian Bases, PDFs + Tesseract OCR. 46 tools, 19 MCP prompts, MIT, SLSA L2, zero cloud calls during serve. npx -y @oomkapwn/enquire-mcp serve --vault
Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall. Non-lossy capture with secret redaction; works across Claude Code, Codex, Cursor, and any MCP host. uvx agentcairn
Tools & Capabilities Breakdown
Enquire MCP Tools (6)
Hybrid retrieval: BM25, ML embeddings, BGE reranker with RRF fusion
Supports Markdown, PDFs with Tesseract OCR, Canvas, Dataview, and Bases
Returns source paths, page citations, age_days, and stale flags
Read-only by default with optional write tools behind a flag
Zero outbound network calls during serving
Agent-agnostic, vendor-neutral MCP server
Agentcairn Tools (6)
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Enquire MCP is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Agentcairn belongs to Knowledge & Memory using local stdio subprocess. Select Enquire MCP when you need capabilities focused on knowledge & memory and Agentcairn when you require tools for knowledge & memory.